The goal of generic multimodal summarization is to extract the most important information from different modalities to form summaries. Yet the importance of scenes and text in a video is often subjective, and users should have the option of customizing the summary by using natural language to specify what is important to them. However, existing methods for fully automatic multimodal summarization have not exploited available language models, which can serve as an effective prior for saliency. To address this issue, we introduce Query-Focused Multimodal Summ arization(QFSumm), a single framework for addressing both generic and query-focused multimodal summarization, typically approached separately in the literature. In addition, we propose a novel gate-guided mixture-of-experts that uses expert gate module to organize three experts (video expert, text expert and shared expert) to model the correlations between multimodal information. In addition, we propose two novel contrastive losses to represent consistency and diversity. Extensive experiments on a query-focused video summarization dataset (QFVS), two standard video summarization datasets (TVSum and SumMe) and three multimodal summarization datasets (CNN, Daily Mail and BLiSS) demonstrate the superiority of QFSumm, achieving state-of-the-art performances on all datasets.

Synthetic graph datasets are crucial for the assessment of network analysis algorithms, providing a measure of their effectiveness and efficiency. However, most existing generation techniques typically focus on community formation, neglecting the fact that real-world communities not only emerge but may also dissipate over time. This lifecycle occurs within a finite timeframe, adding complexity to the community dynamics. In this paper, firstly we introduce the concept of time-bound community to characterize communities that are destined to disintegrate. Secondly, we devise GTB, a temporal graph Generation method featuring Time-Bound communities, leveraging newly identified patterns within real datasets that we have collected. Additionally, we propose the advanced Temporal Edge Distribution (TED) model, a key component of G TB, designed for the swift generation of temporal edges within distribution limits and offering a constant time complexity to generate each edge. The TED model not only accommodates diverse distribution configurations but also facilitates its seamless transfer between time-bound communities to enhance time and space efficiency. Finally, extensive experimental results demonstrate that our method outperforms baseline methods by delivering generated content of superior Quality with notably competitive time and space consumption.